Comments (3)
Greetings.
Usually this error message indicates that you are sending a uint8
type input to the model and not floats. Which may indicate that you don't have any image normalization. And indeed based on your code you are not using any transformations in training/validation datasets. You will get poor results.
Please follow your tutorial notebook on fine-tuning the YoloNAS-Pose: https://github.com/Deci-AI/super-gradients/blob/master/notebooks/YoloNAS_Pose_Fine_Tuning_Animals_Pose_Dataset.ipynb
from super-gradients.
thank you, will update with results.
Normalize in this context means turning pixel coordinates into floats proportional to the image?
from super-gradients.
Thank you, I was missing the normalization transform from the example. appreciate the prompt response sir!
from super-gradients.
Related Issues (20)
- How to improve api access speed HOT 3
- how to apply post process on openvino inference? HOT 2
- yolo-nas performace HOT 4
- Installation error: error: subprocess-exited-with-error HOT 1
- removing label names and confidence in predicted picture HOT 1
- AttributeError: 'EarlyStop' object has no attribute 'append' HOT 1
- Yolo Onnx Export -> Experiencing Worse Accuracy HOT 10
- Python 3.11 HOT 2
- YOLO-NAS - TorchScript output tensor format HOT 1
- onnx export error: MemoryError: std::bad_alloc in onnxsim HOT 2
- YOLO NAS: inference time depending on training? HOT 4
- How to set the lr_warmup_epochs to be greater than 10 ? HOT 2
- Onnx model supporting batch prediction HOT 3
- Possible to use OBS Virtual Webcam as input without capture frame by frame method? HOT 1
- Unable To Load Datasets via adapters for use with YOLO_NAS models HOT 1
- "DetectionMosaic": {"input_dim": [640, 640], "prob": 0.5} messing up the image size in trainloader HOT 1
- How to define a search space
- `super_gradients.training.utils.predict.prediction_pose_estimation_results.ImagePoseEstimationPrediction.save()` not correctly handling optional parameters and saving image incorrectly
- Fine tuning HyperParameters HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from super-gradients.